merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

Qwen/Qwen2.5-7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: Qwen/Qwen2.5-7B
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	31.78
IFEval (0-Shot)	62.64
BBH (3-Shot)	36.32
MATH Lvl 5 (4-Shot)	32.33
GPQA (0-shot)	9.51
MuSR (0-shot)	11.50
MMLU-PRO (5-shot)	38.39

Downloads last month: 16

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Sakalti/model-3

Qwen/Qwen2.5-7B

Qwen/Qwen2.5-7B-Instruct

Merge model

this model

Finetunes

2 models

Merges

4 models

Space using Sakalti/model-3 1

Paper for Sakalti/model-3

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 15

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

62.640
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

36.320
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

32.330
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

9.510
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

11.500
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

38.390